Advanced search
Start date
Betweenand

Understanding images and deep learning models

Abstract

A central goal in the field of Computer Vision is image understanding. In general, appearance cues are used to detect components of interest and then spatial and hierarchical relations among these components are used to "describe" the image content at the semantic level of interest. Current deep models have reached a stage of evolution in which they are able to learn and transfer low level features from one domain to another. However, structural information of images such as spatial and hierarchical relations between constituent components are still explicitly modeled using case specific details. This makes models harder to be understood, useful only for few specific applications, and implications on training data preparation effort is still unclear. The aim of this project is the development of a structure-aware-semantics-unaware deep model, with abilities to learn and encode structural information regardless of the semantic level of image components. This should impact model understandability (as structural information would be more explicitly encoded) and training data requirements (as transfer learning would be possible). Theoretical studies, development of visualization strategies and new deep models, and experimentation with respect to diverse computer vision tasks are planned. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
El avance del aprendizaje de máquinas genera nuevas tecnologías basadas en el análisis de imágenes 
Advances in machine learning enable new technologies based on image analysis 
Articles published in other media outlets (2 total):
Sociedade Científica: Técnica para detecção de parasitas baseada em inteligência artificial é mais eficaz que as convencionais (27/Nov/2019)
NewsLab online: Método para detectar parasitas baseado em inteligência artificial é mais eficaz que técnicas convencionais (26/Nov/2019)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
ESPADOTO, MATEUS; MARTINS, RAFAEL M.; KERREN, ANDREAS; HIRATA, NINA S. T.; TELEA, ALEXANDRU C. Toward a Quantitative Survey of Dimension Reduction Techniques. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, v. 27, n. 3, p. 2153-2173, MAR 1 2021. Web of Science Citations: 3.

Please report errors in scientific publications list by writing to: cdi@fapesp.br.